NyssaW/github-issues

--- dataset_info: features: - name: url dtype: string - name: repository_url dtype: string - name: labels_url dtype: string - name: comments_url dtype: string - name: events_url dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: node_id dtype: string - name: number dtype: int64 - name: title dtype: string - name: user struct: - name: avatar_url dtype: string - name: events_url dtype: string - name: followers_url dtype: string - name: following_url dtype: string - name: gists_url dtype: string - name: gravatar_id dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: login dtype: string - name: node_id dtype: string - name: organizations_url dtype: string - name: received_events_url dtype: string - name: repos_url dtype: string - name: site_admin dtype: bool - name: starred_url dtype: string - name: subscriptions_url dtype: string - name: type dtype: string - name: url dtype: string - name: user_view_type dtype: string - name: labels list: - name: color dtype: string - name: default dtype: bool - name: description dtype: string - name: id dtype: int64 - name: name dtype: string - name: node_id dtype: string - name: url dtype: string - name: state dtype: string - name: locked dtype: bool - name: assignees list: - name: avatar_url dtype: string - name: events_url dtype: string - name: followers_url dtype: string - name: following_url dtype: string - name: gists_url dtype: string - name: gravatar_id dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: login dtype: string - name: node_id dtype: string - name: organizations_url dtype: string - name: received_events_url dtype: string - name: repos_url dtype: string - name: site_admin dtype: bool - name: starred_url dtype: string - name: subscriptions_url dtype: string - name: type dtype: string - name: url dtype: string - name: user_view_type dtype: string - name: milestone struct: - name: closed_at dtype: string - name: closed_issues dtype: int64 - name: created_at dtype: string - name: creator struct: - name: avatar_url dtype: string - name: events_url dtype: string - name: followers_url dtype: string - name: following_url dtype: string - name: gists_url dtype: string - name: gravatar_id dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: login dtype: string - name: node_id dtype: string - name: organizations_url dtype: string - name: received_events_url dtype: string - name: repos_url dtype: string - name: site_admin dtype: bool - name: starred_url dtype: string - name: subscriptions_url dtype: string - name: type dtype: string - name: url dtype: string - name: user_view_type dtype: string - name: description dtype: string - name: due_on dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: labels_url dtype: string - name: node_id dtype: string - name: number dtype: int64 - name: open_issues dtype: int64 - name: state dtype: string - name: title dtype: string - name: updated_at dtype: string - name: url dtype: string - name: comments list: string - name: created_at dtype: timestamp[us, tz=UTC] - name: updated_at dtype: timestamp[us, tz=UTC] - name: closed_at dtype: timestamp[us, tz=UTC] - name: assignee struct: - name: avatar_url dtype: string - name: events_url dtype: string - name: followers_url dtype: string - name: following_url dtype: string - name: gists_url dtype: string - name: gravatar_id dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: login dtype: string - name: node_id dtype: string - name: organizations_url dtype: string - name: received_events_url dtype: string - name: repos_url dtype: string - name: site_admin dtype: bool - name: starred_url dtype: string - name: subscriptions_url dtype: string - name: type dtype: string - name: url dtype: string - name: user_view_type dtype: string - name: author_association dtype: string - name: issue_field_values list: 'null' - name: type dtype: float64 - name: active_lock_reason dtype: float64 - name: draft dtype: float64 - name: pull_request struct: - name: diff_url dtype: string - name: html_url dtype: string - name: merged_at dtype: string - name: patch_url dtype: string - name: url dtype: string - name: body dtype: string - name: closed_by struct: - name: avatar_url dtype: string - name: events_url dtype: string - name: followers_url dtype: string - name: following_url dtype: string - name: gists_url dtype: string - name: gravatar_id dtype: string - name: html_url dtype: string - name: id dtype: int64 - name: login dtype: string - name: node_id dtype: string - name: organizations_url dtype: string - name: received_events_url dtype: string - name: repos_url dtype: string - name: site_admin dtype: bool - name: starred_url dtype: string - name: subscriptions_url dtype: string - name: type dtype: string - name: url dtype: string - name: user_view_type dtype: string - name: reactions struct: - name: '+1' dtype: int64 - name: '-1' dtype: int64 - name: confused dtype: int64 - name: eyes dtype: int64 - name: heart dtype: int64 - name: hooray dtype: int64 - name: laugh dtype: int64 - name: rocket dtype: int64 - name: total_count dtype: int64 - name: url dtype: string - name: timeline_url dtype: string - name: performed_via_github_app dtype: float64 - name: state_reason dtype: string - name: sub_issues_summary struct: - name: completed dtype: int64 - name: percent_completed dtype: int64 - name: total dtype: int64 - name: issue_dependencies_summary struct: - name: blocked_by dtype: int64 - name: blocking dtype: int64 - name: total_blocked_by dtype: int64 - name: total_blocking dtype: int64 - name: pinned_comment dtype: float64 - name: is_Issue dtype: string - name: is_Pull_request dtype: string splits: - name: train num_bytes: 50147641 num_examples: 8041 download_size: 39057835 dataset_size: 50147641 configs: - config_name: default data_files: - split: train path: data/train-* ---dataset_info: 特征字段: - 字段名称: "url"，数据类型: 字符串 - 字段名称: "repository_url"，数据类型: 字符串 - 字段名称: "labels_url"，数据类型: 字符串 - 字段名称: "comments_url"，数据类型: 字符串 - 字段名称: "events_url"，数据类型: 字符串 - 字段名称: "html_url"，数据类型: 字符串 - 字段名称: "id"，数据类型: 64位整数 - 字段名称: "node_id"，数据类型: 字符串 - 字段名称: "number"，数据类型: 64位整数 - 字段名称: "title"，数据类型: 字符串 - 字段名称: "user"，数据类型: 结构体: - 字段名称: "avatar_url"，数据类型: 字符串 - 字段名称: "events_url"，数据类型: 字符串 - 字段名称: "followers_url"，数据类型: 字符串 - 字段名称: "following_url"，数据类型: 字符串 - 字段名称: "gists_url"，数据类型: 字符串 - 字段名称: "gravatar_id"，数据类型: 字符串 - 字段名称: "html_url"，数据类型: 字符串 - 字段名称: "id"，数据类型: 64位整数 - 字段名称: "login"，数据类型: 字符串 - 字段名称: "node_id"，数据类型: 字符串 - 字段名称: "organizations_url"，数据类型: 字符串 - 字段名称: "received_events_url"，数据类型: 字符串 - 字段名称: "repos_url"，数据类型: 字符串 - 字段名称: "site_admin"，数据类型: 布尔值 - 字段名称: "starred_url"，数据类型: 字符串 - 字段名称: "subscriptions_url"，数据类型: 字符串 - 字段名称: "type"，数据类型: 字符串 - 字段名称: "url"，数据类型: 字符串 - 字段名称: "user_view_type"，数据类型: 字符串 - 字段名称: "labels"，数据类型: 列表，列表项结构体: - 字段名称: "color"，数据类型: 字符串 - 字段名称: "default"，数据类型: 布尔值 - 字段名称: "description"，数据类型: 字符串 - 字段名称: "id"，数据类型: 64位整数 - 字段名称: "name"，数据类型: 字符串 - 字段名称: "node_id"，数据类型: 字符串 - 字段名称: "url"，数据类型: 字符串 - 字段名称: "state"，数据类型: 字符串 - 字段名称: "locked"，数据类型: 布尔值 - 字段名称: "assignees"，数据类型: 列表，列表项结构体与上述user结构体一致 - 字段名称: "milestone"，数据类型: 结构体: - 字段名称: "closed_at"，数据类型: 字符串 - 字段名称: "closed_issues"，数据类型: 64位整数 - 字段名称: "created_at"，数据类型: 字符串 - 字段名称: "creator"，数据类型: 结构体与上述user结构体一致 - 字段名称: "description"，数据类型: 字符串 - 字段名称: "due_on"，数据类型: 字符串 - 字段名称: "html_url"，数据类型: 字符串 - 字段名称: "id"，数据类型: 64位整数 - 字段名称: "labels_url"，数据类型: 字符串 - 字段名称: "node_id"，数据类型: 字符串 - 字段名称: "number"，数据类型: 64位整数 - 字段名称: "open_issues"，数据类型: 64位整数 - 字段名称: "state"，数据类型: 字符串 - 字段名称: "title"，数据类型: 字符串 - 字段名称: "updated_at"，数据类型: 字符串 - 字段名称: "url"，数据类型: 字符串 - 字段名称: "comments"，数据类型: 字符串列表 - 字段名称: "created_at"，数据类型: 微秒级、协调世界时（UTC）时区的时间戳 - 字段名称: "updated_at"，数据类型: 微秒级、协调世界时（UTC）时区的时间戳 - 字段名称: "closed_at"，数据类型: 微秒级、协调世界时（UTC）时区的时间戳 - 字段名称: "assignee"，数据类型: 结构体与上述user结构体一致 - 字段名称: "author_association"，数据类型: 字符串 - 字段名称: "issue_field_values"，数据类型: 空列表 - 字段名称: "type"，数据类型: 64位浮点数 - 字段名称: "active_lock_reason"，数据类型: 64位浮点数 - 字段名称: "draft"，数据类型: 64位浮点数 - 字段名称: "pull_request"，数据类型: 拉取请求（Pull Request）结构体: - 字段名称: "diff_url"，数据类型: 字符串 - 字段名称: "html_url"，数据类型: 字符串 - 字段名称: "merged_at"，数据类型: 字符串 - 字段名称: "patch_url"，数据类型: 字符串 - 字段名称: "url"，数据类型: 字符串 - 字段名称: "body"，数据类型: 字符串 - 字段名称: "closed_by"，数据类型: 结构体与上述user结构体一致 - 字段名称: "reactions"，数据类型: 结构体: - 字段名称: "+1"，数据类型: 64位整数 - 字段名称: "-1"，数据类型: 64位整数 - 字段名称: "confused"，数据类型: 64位整数 - 字段名称: "eyes"，数据类型: 64位整数 - 字段名称: "heart"，数据类型: 64位整数 - 字段名称: "hooray"，数据类型: 64位整数 - 字段名称: "laugh"，数据类型: 64位整数 - 字段名称: "rocket"，数据类型: 64位整数 - 字段名称: "total_count"，数据类型: 64位整数 - 字段名称: "url"，数据类型: 字符串 - 字段名称: "timeline_url"，数据类型: 字符串 - 字段名称: "performed_via_github_app"，数据类型: 64位浮点数 - 字段名称: "state_reason"，数据类型: 字符串 - 字段名称: "sub_issues_summary"，数据类型: 结构体: - 字段名称: "completed"，数据类型: 64位整数 - 字段名称: "percent_completed"，数据类型: 64位整数 - 字段名称: "total"，数据类型: 64位整数 - 字段名称: "issue_dependencies_summary"，数据类型: 结构体: - 字段名称: "blocked_by"，数据类型: 64位整数 - 字段名称: "blocking"，数据类型: 64位整数 - 字段名称: "total_blocked_by"，数据类型: 64位整数 - 字段名称: "total_blocking"，数据类型: 64位整数 - 字段名称: "pinned_comment"，数据类型: 64位浮点数 - 字段名称: "is_Issue"，数据类型: 字符串，用于标识是否为议题（Issue） - 字段名称: "is_Pull_request"，数据类型: 字符串，用于标识是否为拉取请求（Pull Request） 数据集划分: - 划分名称: "train"，字节占用量: 50147641，样本总数: 8041 下载大小: 39057835，数据集总字节数: 50147641 配置项: - 配置名称: "default"，数据文件: - 划分: "train"，文件路径: "data/train-*"